Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution

arXiv:2610.19495 · cs.RO, cs.CV · Submitted 2026-10-14 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 34 pages, 14 figures. Project page: https://robota-ai.github.io/robota-embed/

Project page: https://robota-ai.github.io/robota-embed

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 7 episodes

Sources

• Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video
• Contrastive Language, Action, and State Pre-training for Robot Learning
• World Action Models are Zero-shot Policies
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
• WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
• Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving
• Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs
• RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
• Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation
• Retrieval-Augmented Robots via Retrieve-Reason-Act
• Robots Acquire Manipulation Skills in Seconds from a Single Human Video
• Cosmos 3: Omnimodal World Models for Physical AI
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
• RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
• T-Rex: Tactile-Reactive Dexterous Manipulation
• Qwen3-VL Technical Report

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies